On the role of geometry in geo-localization

Consider the geo-localization task of finding the pose of a camera in a large 3 D scene from a single image. Most existing CNN-based methods use as input textured images. We aim to experimentally explore whether texture and correlation between nearby images are necessary in a CNN-based solution for the geo-localization task.To do so, we consider lean images, textureless projections of a simple 3 D model of a city. They only contain information related to the geometry of the scene viewed(edges, faces, and relative depth). The main contributions of this paper are:(i) to demonstrate the ability of CNNs to recover camera pose using lean images; and(ii) to provide insight into the role of geometry in the CNN learning process.